Library
Everything we've written about engineering with agents
Guides, model data, comparisons, and free tools, all maintained against verified sources.
Guides
Agentic engineering, orchestration workflow, and how to get the most out of your coding agents.
The AIDEN Manifesto
Nine principles for building software with AI agents in 2026.
What is an agentic IDE?
The pillar guide: how agentic IDEs work and how they differ from chat IDEs.
What is an agentic development environment (ADE)?
The category above the editor: the six layers that turn raw agents into shippable work.
ADE vs agentic IDE vs AI IDE
Three terms, three scopes. What each one means and which one you actually want.
Local agentic development environment
Run agents on your own machine: BYOK, code that never leaves your filesystem, self-host.
Best agentic IDEs in 2026
AIDEN, Cursor, Windsurf, Devin, Kiro, Cline and Claude Code, compared honestly.
Claude Code orchestration
Run several Claude Code sessions in parallel with a board, branches, and PRs.
Parallel agents with git worktrees
How worktrees isolate agents on separate branches, manually, then automated.
Multi-agent coding workflow
Design a workflow where several AI agents ship in parallel without chaos.
AI PR automation
From feature to reviewed pull request: automating the git workflow around agents.
Engineering with AI agents
Why vibecoding breaks at scale, and the workflow that replaces it.
Spec-driven AI development
Give every agent a written, approved plan before it touches your code.
The AI agent harness
The six conventions AIDEN wraps around raw coding agents, and why.
What is an MCP server?
The definition: host/client/server, the three primitives, transports, and a first server.
MCP servers for AI coding
What MCP is, the servers worth installing, and how AIDEN inherits your setup.
AI kanban for developers
One board where every agent is a card with a branch, a status, and a diff.
Voice orchestrator
Push-to-talk control of your agents: delegate, approve, and review by voice.
What is vibe coding?
The definition, Karpathy's origin, where it shines, and where it breaks.
What is an agentic workflow?
The stages, the five core patterns, and a worked software example.
Agentic loops
The gather-decide-act-observe cycle coding agents run, and how to bound it.
Agent skills (SKILL.md)
Reusable procedural know-how the model loads on demand, and how it differs from MCP.
Model routing for coding agents
Plan with a frontier model, delegate execution to cheaper ones. Cut cost, keep quality.
Agentic graphs
Model an agent system as nodes and edges: branches, joins, loops, and shared state.
Spec-driven kanban
A board where every card carries an approved spec before an agent touches code.
Agile with AI agents
The values survive but the mechanics compress. Scrum reimagined for coding agents.
AI spec file
The short, reviewable doc that tells a coding agent what to build and how you'll judge it.
AI project management prompt
A copy-paste prompt that turns Claude Code or Codex into a PM: epics, features, approval gates.
Sprint planning with AI agents
The bottleneck moves from dev hours to spec quality and review capacity. Plan for it.
Best MCP servers for frontend
Which MCP servers actually help when your coding agent is doing React, CSS, and browser work.
Best MCP servers for backend
Which MCP servers matter for APIs, DBs, and background jobs — scored on real DX gain.
Best MCP servers for DevOps
MCP servers that matter for infra, CI/CD, and incident response with coding agents.
Best MCP servers for data
Which MCP servers help agents work with SQL, warehouses, and analytics pipelines.
Best agent skills for frontend
The SKILL.md categories worth writing for React, CSS, and browser work.
Best agent skills for backend
The SKILL.md categories worth writing for APIs, DBs, and backend infra.
Best agent skills for testing
The SKILL.md categories that stop agents from mocking the test to make it pass.
Claude Code and Codex together
The dual-agent workflow: which tool takes which task, and how to run both on one project.
Manage multiple Claude Code sessions
From terminal tabs to worktrees to a board: scaling past one agent without losing track.
A GUI for Claude Code
A desktop interface for the Claude Code CLI you already run: a board, parallel agents, a worktree per feature.
Claude Code on Windows
It runs on Windows today: the install, the native-versus-WSL2 call, and where AIDEN's Windows build stands.
A kanban board for Claude Code
Why a board is the right UI for agent sessions, and how AIDEN maps features to agents.
Claude Code usage limits, explained
How the limits work, how parallel agents change the math, and how to stretch a plan.
Codex usage limits & credits
How Codex plans and credits work, and how to budget agent work across them.
Claude Code tutorial
From install to parallel agents: a practical, current guide to working with Claude Code.
Claude Code Agent Teams
Anthropic's experimental multi-session orchestration, and when you need more than it.
Desktop apps for coding agents
The 2026 landscape: Conductor, Sculptor, the Codex app, AIDEN, and how to choose.
What is agentic engineering?
The discipline replacing vibe coding: orchestrating agents with specs, gates, and review.
Vibe coding vs agentic engineering
Same tools, opposite disciplines. Where each fits and where each breaks.
Is vibe coding dead?
What actually happened to vibe coding in 2026, and what replaced it in production teams.
Context engineering for coding agents
The craft of feeding agents the right context: files, specs, memory, and isolation.
Issue tracking for AI agents
Why agents need trackers more than humans do, and what an agent-native tracker looks like.
Project management for AI agents
Not AI helping PMs, PM for teams where the assignees are coding agents.
How to assign tasks to AI agents
The issue-to-agent-to-PR pattern across Linear, GitHub, and AIDEN's feature board.
Linear + Claude Code
How to connect them today, and the shortcut: a board and agents in one app.
AI models
Every current Claude and GPT coding model: pricing, benchmarks, and when to use which.
AI models for coding: the hub
Every current Claude and GPT model for coding, prices, benchmarks, and when to use each.
GPT-6 Astra for coding
OpenAI's highest-capability model: verified price, 1.05M context, and when the premium is justified.
GPT-6.1 Sol for coding
OpenAI's recommended Codex model: near-Astra coding at $2/$10 per million tokens.
GPT-6 Sol for coding
The first GPT-6 Sol, superseded by GPT-6.1 Sol at the same $2/$10; still selectable in Codex.
GPT-6 Luna for coding
The efficient GPT-6 tier for repeatable high-volume work at $0.10/$0.50.
Claude Fable 5.1 for coding
Anthropic's frontier escalation: verified pricing, 1M context, and published coding benchmarks.
Claude Opus 5.5 for coding
Anthropic's recommended default and Claude Code's default: $4/$20, 1M context, 128K output, and how Sonnet 5.5 compares.
Claude Fable 5 for coding
Previous-generation Fable model, preserved for migration context and superseded by Fable 5.1.
GPT-5.6 Sol for coding
Previous-generation GPT-5.6 flagship, preserved for migration context and superseded by GPT-6.
Best Claude model for coding
Start with Opus 5.5, then route to Sonnet 5.5, Haiku 5.5 or Fable 5.1 by task: Claude Code settings, effort and a per-task cost calculator.
Best Codex model
GPT-6.1 Sol vs Astra vs Luna: which Codex model and reasoning effort to use, with a per-task cost calculator.
Codex models list
GPT-6.1 Sol, Astra and Luna with verified prices and task fit, plus which older models are leaving Codex.
Claude Opus 5 for coding
Previous-generation Opus model, superseded by Opus 5.5 at a lower $4/$20 base price.
Claude Sonnet 5.5 for coding
Beats Opus 5.5 on Terminal-Bench 4.0 at half the price: $2/$10, $0.10 cache reads, 1M context, and where Opus still wins.
Claude Haiku 5.5 for coding
The fast tier grew up: $0.10/$0.50 per MTok, a 1M window, effort levels, and 39.2% on Terminal-Bench 4.0.
GPT-5.6 Terra for coding
Previous GPT-5.6 workhorse, superseded by GPT-6.1 Sol as OpenAI's recommended Codex model.
GPT-5.6 Luna for coding
Previous GPT-5.6 budget tier, superseded by the cheaper GPT-6 Luna.
Model match-ups
Head-to-head model and tool comparisons with verified data.
GPT-6 Astra vs Sol vs Luna
GPT-6 Astra vs GPT-6.1 Sol vs Luna: price, cached input, context, effort and task fit.
Claude Opus 5.5 vs GPT-6 Astra
The current Claude default and OpenAI frontier model compared with sourced facts and explicit caveats.
Claude Opus 5 vs Claude Fable 5
Previous-generation match-up, both superseded: Opus 5 landed near Fable 5 at half the price.
Claude Opus 5 vs GPT-5.6 Sol
Previous-generation flagship face-off; Opus 5.5 vs GPT-6 Astra covers the current one.
Claude Fable 5 vs GPT-5.6 Sol
The August 2026 flagship match-up, now previous generation on both sides.
Claude Code vs Codex
The two leading coding agents compared by people who run both, daily, in production.
Claude vs GPT for coding
The evergreen model-family comparison: strengths, pricing, and how to decide.
GPT-5.6 Sol vs Terra vs Luna
The GPT-5.6 tiers compared, now previous generation; GPT-6 Astra vs Sol vs Luna covers the current family.
Opus vs Sonnet vs Haiku
The Claude 5.5 tier picker: launch benchmarks, cost per feature, and when each tier earns its price.
AIDEN vs everything
Honest comparisons with the tools you might be using today.
AIDEN vs Cursor
Agent orchestration on a board vs an AI-first editor.
AIDEN vs Windsurf
Parallel worktree orchestration vs the Cascade agent IDE.
AIDEN vs GitHub Copilot
A dedicated orchestration workspace vs Copilot inside your editor.
AIDEN vs Aider
A desktop workspace around the same idea Aider pioneered in the terminal.
AIDEN vs Claude Code
Not a replacement, AIDEN runs your Claude Code CLI, in parallel.
AIDEN vs Codex CLI
Run OpenAI's Codex CLI inside a board-driven desktop workspace.
AIDEN vs Kiro
Two spec-driven IDEs: AWS's VS Code fork vs a BYOK orchestrator.
AIDEN vs Devin
A cloud AI engineer vs local agents you orchestrate yourself.
AIDEN vs Cline
The open-source VS Code agent vs a dedicated multi-agent workspace.
AIDEN vs v0
Full-codebase engineering vs Vercel's UI generation.
AIDEN vs bolt.new
Existing codebases and real git vs in-browser app scaffolding.
AIDEN vs Lovable
Engineer-grade workflows vs prompt-to-app prototyping.
AIDEN vs Replit Agent
Local-first orchestration vs Replit's cloud workspace.
AIDEN vs Copilot coding agent
GitHub's task-to-PR agent vs a local multi-agent workspace.
AIDEN vs Zed
Different axes: editor speed vs agent orchestration.
AIDEN vs Continue
The open-source assistant framework vs a ready-made orchestrator.
Vibe Kanban alternative
Vibe Kanban shut down in April 2026. AIDEN is the maintained, spec-first board for your agents.
Linear alternative for AI teams
Linear is built for human teams. AIDEN is the board for teams where half the assignees are agents.
Terragon alternative
Terragon shut down in February 2026. Run background agents locally instead, on your own machine.
Conductor alternative
Conductor is a solid Mac agent runner. AIDEN adds the spec gate, the feature board, and team mode.
By language
Agent workflows tuned to your stack.
AI IDE for Python
Agents that run pytest and mypy in the loop on Python codebases.
AI IDE for TypeScript
Type-checked agent workflows for TypeScript and Node projects.
AI IDE for JavaScript
Agent workflows for JavaScript apps, from Node services to browser UIs.
AI IDE for Go
Agents that build, vet, and test Go services on parallel branches.
AI IDE for Rust
Borrow-checker-friendly agent workflows for Rust crates and services.
AI IDE for Next.js
Full-stack agent workflows for Next.js apps, with live preview built in.
Free tools
Generators, validators, and templates. No signup.
Free tools for AI-agent development
Generators, validators, templates, and a glossary, free, no signup.
AGENTS.md / CLAUDE.md generator
Answer a few questions, get a solid context file for your coding agents.
Git worktree setup generator
Copy-paste commands to run parallel agents on isolated worktrees.
Agent spec template builder
Turn a task into a written spec your agent can be held to.
MCP config validator
Paste your MCP JSON, catch mistakes, get the right claude mcp commands.
AIDEN Method skill pack
Free Claude Code skills: spec-first, worktree-per-feature, PR-per-feature.
Feature & spec templates
Battle-tested markdown templates for feature, bugfix, and refactor features.
AI coding glossary
Plain-English definitions: agents, worktrees, MCP, spec gates, and more.
Product
Pricing, changelog, and what is coming next.